Explainable and trustworthy artificial intelligence for correctable modeling in chemical sciences

Abstract

The developed framework apportions model error to inputs, computes predictive guarantees, and enables model correctability.

Document Details

Document Type
Pub Defense Publication
Publication Date
Oct 16, 2020
Source ID
10.1126/sciadv.abc3204

Entities

People

  • Dionisios G. Vlachos
  • Jinchao Feng
  • Joshua L Lansford
  • Markos A Katsoulakis

Organizations

  • Air Force Office of Scientific Research
  • Defense Advanced Research Projects Agency
  • Johns Hopkins University
  • National Science Foundation
  • United States Department of Energy
  • University of Delaware
  • University of Massachusetts Amherst

Tags

Fields of Study

  • Computer science

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference